How graykode/nlp-tutorial works
nlp-tutorial is a PyTorch learning repository: learners study compact, runnable NLP model examples and observe task-specific predictions, classifications, translations, embeddings, or attention visualizations. Its principal workflow is to explore a curriculum example, run its model/training code, and inspect the demonstrated result. The graph groups the documented examples by model family; scripts are largely self-contained rather than components in a shared runtime pipeline. The FastText implementation is represented by its notebook because no Python source file appears in the tree. Archived TensorFlow versions are excluded. Relationships reflect README curriculum links, not unsampled implementation calls.
Main entry points: NNLM.py NNLM · Word2Vec-Skipgram(Softmax).py Word2Vec · FastText.ipynb FastText · TextRNN.py TextRNN
Components 14
Embedding Models
Sequence Models
Attention Models
- Seq2Seq Attention
4-2.Seq2Seq(Attention)/Seq2Seq(Attention).py - Bi-LSTM Attention
4-3.Bi-LSTM(Attention)/Bi-LSTM(Attention).py
Transformer Models
- Transformer
5-1.Transformer/Transformer.py - Greedy Transformer
5-1.Transformer/Transformer(Greedy_decoder).py - BERT
5-2.BERT/BERT.py
Classification
- TextCNN
2-1.TextCNN/TextCNN.py
Other components
- NLP learner
Connections 13
- NLP learner → NNLM: studies example
README.md - NLP learner → Word2Vec: studies example
README.md - NLP learner → FastText: studies example
README.md - NLP learner → TextRNN: studies example
README.md - NLP learner → TextLSTM: studies example
README.md - NLP learner → Bi-LSTM: studies example
README.md - NLP learner → Seq2Seq: studies example
README.md - NLP learner → Seq2Seq Attention: studies example
README.md - NLP learner → Bi-LSTM Attention: studies example
README.md - NLP learner → Transformer: studies example
README.md - NLP learner → Greedy Transformer: studies example
README.md - NLP learner → BERT: studies example
README.md - NLP learner → TextCNN: studies example
README.md